diff --git a/fern/docs.yml b/fern/docs.yml index 5725e33..d34052c 100644 --- a/fern/docs.yml +++ b/fern/docs.yml @@ -25,6 +25,8 @@ navigation: path: ./docs/pages/sdks.mdx - section: Input Requirements contents: + - page: Models + path: ./docs/pages/options/models.mdx - page: Enumerations path: ./docs/pages/options/enumerations.mdx - page: Prompt Formatting diff --git a/fern/docs/pages/options/enumerations.mdx b/fern/docs/pages/options/enumerations.mdx index 3e1a017..9e50d93 100644 --- a/fern/docs/pages/options/enumerations.mdx +++ b/fern/docs/pages/options/enumerations.mdx @@ -17,14 +17,14 @@ This page provides the list of enumerations used by the Prediction Guard API. ### These Models are required in `/completions` and `/chat/completions` endpoints: -| Model Name | Type | Use Case | Prompt Format | Context Length | More Info | -| ---------------------------- | -------------------- | ------------------------------------------------------- | --------------------------------------------- | -------------- | ----------------------------------------------------------------------- | -| Hermes-2-Pro-Llama-3-8B | Chat | Instruction following or chat-like applications | [ChatML](prompts#chatml) | 4096 | [link](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B) | -| Nous-Hermes-Llama2-13B | Text Generation | Generating output in response to arbitrary instructions | [Alpaca](prompts#alpaca) | 4096 | [link](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b) | -| Hermes-2-Pro-Mistral-7B | Chat | Instruction following or chat-like applications | [ChatML](prompts#chatml) | 4096 | [link](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) | -| Neural-Chat-7B | Chat | Instruction following or chat-like applications | [Neural Chat](prompts#neural-chat) | 4096 | [link](https://huggingface.co/Intel/neural-chat-7b-v3-1) | -| llama-3-sqlcoder-8b | SQL Query Generation | Generating SQL queries | [Llama-3-SQLCoder](prompts#llama-3-sqlcoder) | 4096 | [link](https://huggingface.co/defog/llama-3-sqlcoder-8b) | -| deepseek-coder-6.7b-instruct | Code Generation | Generating computer code or answering tech questions | [Deepseek](prompts#deepseek) | 4096 | [link](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) | +| Model Name | Type | Use Case | Prompt Format | Context Length | More Info | +| ---------------------------- | -------------------- | ------------------------------------------------------- | ----------------------------------------------------- | -------------- | ----------------------------------------------------------------------- | +| Hermes-2-Pro-Llama-3-8B | Chat | Instruction following or chat-like applications | [ChatML](/options/prompts#chatml) | 4096 | [link](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B) | +| Nous-Hermes-Llama2-13B | Text Generation | Generating output in response to arbitrary instructions | [Alpaca](/options/prompts#alpaca) | 4096 | [link](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b) | +| Hermes-2-Pro-Mistral-7B | Chat | Instruction following or chat-like applications | [ChatML](/options/prompts#chatml) | 4096 | [link](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) | +| Neural-Chat-7B | Chat | Instruction following or chat-like applications | [Neural Chat](/options/prompts#neural-chat) | 4096 | [link](https://huggingface.co/Intel/neural-chat-7b-v3-1) | +| llama-3-sqlcoder-8b | SQL Query Generation | Generating SQL queries | [Llama-3-SQLCoder](/options/prompts#llama-3-sqlcoder) | 4096 | [link](https://huggingface.co/defog/llama-3-sqlcoder-8b) | +| deepseek-coder-6.7b-instruct | Code Generation | Generating computer code or answering tech questions | [Deepseek](/options/prompts#deepseek) | 4096 | [link](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) | ### This Model is required in the `/embeddings` endpoint: diff --git a/fern/docs/pages/options/models.mdx b/fern/docs/pages/options/models.mdx new file mode 100644 index 0000000..cbf5868 --- /dev/null +++ b/fern/docs/pages/options/models.mdx @@ -0,0 +1,202 @@ +--- +title: Models +description: Reliable, future proof AI predictions +slug: options/models +--- + +This page provides information about the different models used by the Prediction +Guard API. + +### Hermes-2-Pro-Llama-3-8B + +A general use model that maintains excellent general task and conversation +capabilities while excelling at JSON Structured Outputs and improving on several +other metrics. + +``` +Type : Chat +Use Case : Instruction following or chat-like applications +Promp Format: [ChatML](/options/prompts#chatml) +``` + +https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B + +Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of +an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly +introduced Function Calling and JSON Mode dataset developed in-house. + +This new version of Hermes maintains its excellent general task and conversation +capabilities - but also excels at Function Calling, JSON Structured Outputs, +and has improved on several other metrics as well, scoring a 90% on our function +calling evaluation built in partnership with Fireworks.AI, and an 84% on our +structured JSON Output evaluation. + +Hermes Pro takes advantage of a special system prompt and multi-turn function +calling structure with a new chatml role in order to make function calling +reliable and easy to parse. Learn more about prompting below. + +This version of Hermes 2 Pro adds several tokens to assist with agentic +capabilities in parsing while streaming tokens - , , + and their closing tags are single tokens now. + +### Nous-Hermes-Llama2-13B + +A general use model that combines advanced analytics capabilities with a vast 13 +billion parameter count, enabling it to perform in-depth data analysis and +support complex decision-making processes. This model is designed to process +large volumes of data, uncover hidden patterns, and provide actionable insights. + +``` +Type : Text Generation +Use Case : Generating output in response to arbitrary instructions +Promp Format: [Alpaca](/options/prompts#alpaca) +``` + +https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b + +Nous-Hermes-Llama2-13b is a state-of-the-art language model fine-tuned on over +300,000 instructions. This model was fine-tuned by Nous Research, with Teknium +and Emozilla leading the fine tuning process and dataset curation, Redmond AI +sponsoring the compute, and several other contributors. + +This Hermes model uses the exact same dataset as Hermes on Llama-1. This is to +ensure consistency between the old Hermes and new, for anyone who wanted to keep +Hermes as similar to the old one, just more capable. + +This model stands out for its long responses, lower hallucination rate, and +absence of OpenAI censorship mechanisms. The fine-tuning process was performed +with a 4096 sequence length on an 8x a100 80GB DGX machine. + +### Hermes-2-Pro-Mistral-7B + +A general use model that offers advanced natural language understanding and +generation capabilities, empowering applications with high-performance +text-processing functionalities across diverse domains and languages. The model +excels in delivering accurate and contextually relevant responses, making it ideal +for a wide range of applications, including chatbots, language translation, +content creation, and more. + +``` +Type : Chat +Use Case : Instruction following or chat-like applications +Promp Format: [ChatML](/options/prompts#chatml) +``` + +https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B + +Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of +an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly +introduced Function Calling and JSON Mode dataset developed in-house. + +This new version of Hermes maintains its excellent general task and conversation +capabilities - but also excels at Function Calling, JSON Structured Outputs, and +has improved on several other metrics as well, scoring a 90% on our function +calling evaluation built in partnership with Fireworks.AI, and an 84% on our +structured JSON Output evaluation. + +Hermes Pro takes advantage of a special system prompt and multi-turn function +calling structure with a new chatml role in order to make function calling +reliable and easy to parse. Learn more about prompting below. + +### Neural-Chat-7B + +A revolutionary AI model for perfoming digital conversations. + +``` +Type : Chat +Use Case : Instruction following or chat-like applications +Promp Format: [Neural Chat](/options/prompts#neural-chat) +``` + +https://huggingface.co/Intel/neural-chat-7b-v3-3 + +This model is a fine-tuned 7B parameter LLM on the Intel Gaudi 2 processor from +the Intel/neural-chat-7b-v3-1 on the meta-math/MetaMathQA dataset. The model was +aligned using the Direct Performance Optimization (DPO) method with +Intel/orca_dpo_pairs. The Intel/neural-chat-7b-v3-1 was originally fine-tuned +from mistralai/Mistral-7B-v-0.1. For more information, refer to the blog + +[The Practice of Supervised Fine-tuning and Direct Preference Optimization on Intel Gaudi2](https://medium.com/@NeuralCompressor/the-practice-of-supervised-finetuning-and-direct-preference-optimization-on-habana-gaudi2-a1197d8a3cd3). + +### llama-3-sqlcoder-8b + +A state of the art AI model for generating SQL queries from natural language. + +``` +Type : SQL Query Generation +Use Case : Generating SQL queries +Promp Format: [Llama-3-SQLCoder](/options/prompts#llama-3-sqlcoder) +``` + +https://huggingface.co/defog/llama-3-sqlcoder-8b + +A capable language model for text to SQL generation for Postgres, Redshift and +Snowflake that is on-par with the most capable generalist frontier models. + +### deepseek-coder-6.7b-instruct + +DeepSeek Coder is a capable coding model trained on two trillion code and natural +language tokens. + +``` +Type : Code Generation +Use Case : Generating computer code or answering tech questions +Promp Format: [Deepseek](/options/prompts#deepseek) +``` + +https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct + +Deepseek Coder is composed of a series of code language models, each trained +from scratch on 2T tokens, with a composition of 87% code and 13% natural +language in both English and Chinese. We provide various sizes of the code model, +ranging from 1B to 33B versions. Each model is pre-trained on project-level code +corpus by employing a window size of 16K and a extra fill-in-the-blank task, to +support project-level code completion and infilling. For coding capabilities, +Deepseek Coder achieves state-of-the-art performance among open-source code models +on multiple programming languages and various benchmarks. + +### bridgetower-large-itm-mlm-itc + +BridgeTower is a multimodal model for creating joint embeddings between images +and text. + +_*Note: This Model is required to be used with the `/embeddings` endpoint. Most of the +SDKs will not ask you to provide model because it's using this one.*_ + +``` +Type : Embedding Generation +Use Case : Used for generating text and image embedding +``` + +https://huggingface.co/BridgeTower/bridgetower-large-itm-mlm-itc + +BridgeTower introduces multiple bridge layers that build a connection between +the top layers of uni-modal encoders and each layer of the cross-modal encoder. +This enables effective bottom-up cross-modal alignment and fusion between visual +and textual representations of different semantic levels of pre-trained uni-modal +encoders in the cross-modal encoder. Pre-trained with only 4M images, BridgeTower +achieves state-of-the-art performance on various downstream vision-language tasks. +In particular, on the VQAv2 test-std set, BridgeTower achieves an accuracy of +78.73%, outperforming the previous state-of-the-art model METER by 1.09% with +the same pre-training data and almost negligible additional parameters and +computational costs. Notably, when further scaling the model, BridgeTower +achieves an accuracy of 81.15%, surpassing models that are pre-trained on +orders-of-magnitude larger datasets. + +### llava-1.5-7b-hf + +LLaVa is a multimodal model that supports vision and language models combined. + +_*This Model is required to be used with the `/chat/completions` vision endpoint. +Most of the SDKs will not ask you to provide model because it's using this one.*_ + +``` +Type : Vision Text Generation +Use Case : Used for generating text from text and image inputs +``` + +https://huggingface.co/llava-hf/llava-1.5-7b-hf + +LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on +GPT-generated multimodal instruction-following data. It is an auto-regressive +language model, based on the transformer architecture. \ No newline at end of file